K近邻(KNN)算法(二)---实现约会匹配

欢迎点击参观我的 ——> 个人学习网站
参考
测试代码:

import numpy as np
import operator
import matplotlib.pyplot as plt


def fileReader(filename):
    fr = open(filename)
    numlines = len(fr.readlines())
    returnMat = np.zeros((numlines, 3))

    fr = open(filename)
    index = 0
    listLabels = []
    for line in fr.readlines():
        line = line.strip()
        listFromlines = line.split('\t')
        returnMat[index, :] = listFromlines[0:3]
        index += 1
        listLabels.append(int(listFromlines[-1]))
    return returnMat, listLabels

def autoNorm(dataSet):
    minVal = dataSet.min(0)
    maxVal = dataSet.max(0)
    ranges = maxVal - minVal

    normDataSet = np.zeros(np.shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - np.tile(minVal, (m, 1))
    normDataSet = normDataSet / np.tile(ranges, (m, 1))
    return normDataSet

def classfy(testdata, dataSet, labels, k):
    datasize = dataSet.shape[0]
    diffMat = np.tile(testdata, (datasize, 1)) - dataSet
    sqDiff = diffMat ** 2
    sqDistance = sqDiff.sum(axis=1)
    distance = sqDistance ** 0.5
    sortedDistIndicies = distance.argsort()

    classCount = {}
    for i in range(k):
        voteLabel = labels[sortedDistIndicies[i]]
        classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
    sortclassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortclassCount[0][0]




if __name__ == "__main__":
    dataSet, dataLabel = fileReader('D:\Leaarn\MLtest\KNN\data\datingSet.txt')
    normSet = autoNorm(dataSet)

    hoRatio = 0.1
    m = normSet.shape[0]
    numTest = int(hoRatio * m)
    errorCount = 0.0
    for i in range(numTest):
        classifierResult = classfy(normSet[i, :], normSet[numTest:m, :], dataLabel[numTest:m], 3)
        print "the classifier answer: %d, the real answer is: %d" %(classifierResult, dataLabel[i])
        if (classifierResult!=dataLabel[i]):
            errorCount += 1.0
        print "The total error rate is : %f" %(errorCount/float(numTest))